Amplitude displacement quantization model training method and device for cable-structured flexible photovoltaic support

Abstract

The present application discloses a method and device for training an amplitude displacement quantification model of a cable-structured flexible photovoltaic support. Among them, a six-axis sensor is provided on the cable-structured flexible photovoltaic support, and the six-axis sensor is used to monitor its motion state information in three-dimensional space, by obtaining historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; based on the vibration video information, the actual amplitude displacement information of the cable-structured flexible photovoltaic support in the historical period is determined; based on the historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, the initial neural network model is iteratively trained to obtain an amplitude displacement quantification model; the amplitude displacement quantification model can determine the amplitude displacement of the cable-structured flexible photovoltaic support based on data such as the main cable structure parameters. The present application can achieve high-precision amplitude displacement monitoring by deploying a six-axis sensor alone, reducing the vibration monitoring cost of the cable-structured flexible photovoltaic support.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic support. Background Art

[0002] With the rapid development of photovoltaic power generation technology, the performance and stability of photovoltaic support systems, as a key part of supporting photovoltaic modules, directly affect the efficiency and life of photovoltaic power generation systems. Although traditional fixed supports have simple structures and are easy to install, their adaptability and stability are obviously insufficient in complex terrain and harsh climatic conditions.

[0003] Therefore, the cable-structured flexible photovoltaic bracket has gradually become a research hotspot due to its unique flexible design and ability to better adapt to complex terrain. The cable-structured flexible photovoltaic bracket can support and adjust photovoltaic modules through a flexible cable structure. It not only has excellent terrain adaptability, but also exhibits stronger wind-vibration resistance. However, since the cable-structured flexible photovoltaic bracket is more complex, its wind-vibration characteristics are difficult to effectively simulate through numerical simulation, and it is difficult to quantify the vibration of the cable-structured photovoltaic bracket, resulting in the inability to accurately evaluate the impact of vibration on power generation efficiency and module life.

[0004] Based on this, there is an urgent need for a high-precision method to quantify the vibration of cable-structured photovoltaic brackets, so as to achieve low-cost and high-precision monitoring of the amplitude displacement of cable-structured flexible photovoltaic brackets. Summary of the invention

[0005] Based on the above problems, the present application provides a method and device for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic bracket, with the aim of achieving high-precision amplitude displacement monitoring by separately deploying six-axis sensors and reducing the vibration monitoring cost of the cable-structured flexible photovoltaic bracket.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] In a first aspect of the present application, a method for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic bracket is provided, wherein a six-axis sensor is provided on a main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket, and the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic bracket in a three-dimensional space, and the method comprises: obtaining historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; the historical main cable structure parameters are the structure parameters of the main cable in a historical period, the historical meteorological information is the meteorological information of a target area in the historical period, the historical motion state information is the motion state information of the cable-structured flexible photovoltaic bracket in the historical period, and the vibration video information is used to characterize the actual vibration of the cable-structured flexible photovoltaic bracket in the historical period, and the target area is the area where the cable-structured flexible photovoltaic bracket is located;

[0008] Based on the vibration video information, determining the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period;

[0009] Based on the historical main cable structure parameters, the historical meteorological information, the historical motion state information and the actual amplitude displacement information, the initial neural network model is iteratively trained to obtain an amplitude displacement quantization model; the amplitude displacement quantization model is used to determine the amplitude displacement of the cable structure flexible photovoltaic bracket based on the main cable structure parameters, motion state information and meteorological information.

[0010] In an optional implementation, the X-axis of the six-axis sensor is in the same direction as the support beam of the cable structure flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the motion state information includes:

[0011] Acceleration information of the cable-structured flexible photovoltaic support along the X-axis, the Y-axis and the Z-axis respectively;

[0012] The cable-structured flexible photovoltaic support has angular velocity information along the X-axis, the Y-axis and the Z-axis respectively.

[0013] In an optional implementation, the main cable structural parameters include the inclination angle between the main cable and the ground, the load-bearing capacity and length of the main cable; and the meteorological information includes wind speed information and wind direction information.

[0014] In an optional implementation, the vibration video information includes the longitudinal vibration video collected by the first visual sensor during the historical period, and the lateral vibration video collected by the second visual sensor during the historical period, the first visual sensor is located on the side of the single span of the cable-structured flexible photovoltaic support, and the second visual sensor is located below the middle of the single span of the cable-structured flexible photovoltaic support, and the center of the pictures collected by the first visual sensor and the second visual sensor are both the positions of the six-axis sensor.

[0015] In an optional implementation, the actual amplitude displacement information includes an actual longitudinal amplitude displacement and an actual lateral amplitude displacement, and determining the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period based on the vibration video information includes:

[0016] Acquire a first camera parameter, a second camera parameter, a first target distance, and a second target distance; the first camera parameter is an internal parameter of the first visual sensor, the second camera parameter is an internal parameter of the second visual sensor, the first target distance is a distance between the first visual sensor and the six-axis sensor, and the second target distance is a distance between the second visual sensor and the six-axis sensor;

[0017] Based on the first camera parameter and the first target distance, performing video analysis on the longitudinal vibration video to obtain the actual longitudinal amplitude displacement;

[0018] Based on the second camera parameter and the second target distance, video analysis is performed on the lateral vibration video to obtain the actual lateral amplitude displacement.

[0019] In an optional implementation, after determining the amplitude displacement of the cable structure flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information, the method further includes:

[0020] Constructing a time series data table based on the motion state information, the meteorological information, the main cable structure parameters and the amplitude displacement;

[0021] Data analysis is performed on the time series data table to obtain analysis results; the analysis results are used to evaluate the operating status of the cable structure flexible photovoltaic support.

[0022] In a second aspect of the present application, an amplitude displacement quantization model training device for a cable-structured flexible photovoltaic support is provided, wherein a six-axis sensor is provided on a main cable in the middle of a single span of the cable-structured flexible photovoltaic support, and the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic support in a three-dimensional space, and the device comprises:

[0023] An acquisition module is used to acquire historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; the historical main cable structure parameters are the structure parameters of the main cable in a historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable structure flexible photovoltaic support in the historical period, the vibration video information is used to characterize the actual vibration of the cable structure flexible photovoltaic support in the historical period, and the target area is the area where the cable structure flexible photovoltaic support is located;

[0024] A determination module, used to determine actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period based on the vibration video information;

[0025] A training module is used to iteratively train the initial neural network model based on the historical main cable structure parameters, the historical meteorological information, the historical motion state information and the actual amplitude displacement information to obtain an amplitude displacement quantification model; the amplitude displacement quantification model is used to determine the amplitude displacement of the cable structure flexible photovoltaic bracket based on the main cable structure parameters, motion state information and meteorological information.

[0026] Optionally, the X-axis of the six-axis sensor is in the same direction as the support beam of the cable-structured flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the motion state information includes:

[0027] Acceleration information of the cable-structured flexible photovoltaic support along the X-axis, the Y-axis and the Z-axis respectively;

[0028] The cable-structured flexible photovoltaic support has angular velocity information along the X-axis, the Y-axis and the Z-axis respectively.

[0029] In a third aspect of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the amplitude displacement quantization model training method of the above-mentioned cable-structured flexible photovoltaic support is implemented.

[0030] In a fourth aspect of the present application, a processor is provided for running a computer program, and when the computer program is running, the amplitude displacement quantization model training method of the cable-structured flexible photovoltaic support is executed.

[0031] Compared with the prior art, this application has the following beneficial effects:

[0032] In the technical solution of the present application, a six-axis sensor is provided on the main cable in the middle of a single span of a cable-structured flexible photovoltaic bracket, and the six-axis sensor can be used to monitor the motion state information of the cable-structured flexible photovoltaic bracket in three-dimensional space; by obtaining historical main cable structural parameters, historical meteorological information, historical motion state information and vibration video information; then based on the vibration video information, the actual amplitude displacement information of the cable-structured flexible photovoltaic bracket in the historical period is determined; finally, based on the historical main cable structural parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, the initial neural network model is iteratively trained to obtain an amplitude displacement quantification model; wherein the historical main cable structural parameters are the structural parameters of the main cable in the historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable-structured flexible photovoltaic bracket in the historical period, the vibration video information is used to characterize the actual vibration of the cable-structured flexible photovoltaic bracket in the historical period, the target area is the area where the cable-structured flexible photovoltaic bracket is located, and the amplitude displacement quantification model is used to determine the amplitude displacement of the cable-structured flexible photovoltaic bracket based on the main cable structural parameters, motion state information and meteorological information.

[0033] In the technical solution of the present application, since the middle of a single span is usually the position where the deflection of the cable-structured flexible photovoltaic bracket is the largest and the amplitude is the most obvious, by setting a six-axis sensor on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket, the vibration of the cable-structured flexible photovoltaic bracket can be captured more accurately; since the vibration video information can characterize the actual vibration of the cable-structured flexible photovoltaic bracket in a historical period, the actual amplitude displacement information of the cable-structured flexible photovoltaic bracket can be accurately determined based on the vibration video information, and thus the initial neural network model is iteratively trained based on the historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, so as to obtain a high-precision amplitude displacement quantification model; and then, it is only necessary to deploy a six-axis sensor on the cable-structured flexible photovoltaic bracket, and the amplitude displacement of the cable-structured flexible photovoltaic bracket can be accurately determined through the trained amplitude displacement quantification model based on the motion state information collected by the six-axis sensor and the main cable structure parameters and meteorological information corresponding to the cable-structured flexible photovoltaic bracket, thereby realizing high-precision amplitude displacement monitoring by deploying a single six-axis sensor, and reducing the vibration monitoring cost of the cable-structured flexible photovoltaic bracket. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0035] Figure 1 A flowchart of an amplitude displacement quantization model training method for a cable-structured flexible photovoltaic support provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of the structure of an amplitude displacement quantization system provided in an embodiment of the present application;

[0037] Figure 3 A schematic diagram of the structure of a cable-structured flexible photovoltaic support provided in an embodiment of the present application;

[0038] Figure 4 A flowchart of a process for determining actual amplitude displacement information provided in an embodiment of the present application;

[0039] Figure 5 A flowchart of a training process of an amplitude displacement quantization model provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of another cable-structured flexible photovoltaic support provided in an embodiment of the present application;

[0041] Figure 7 A flowchart of a process for determining an amplitude displacement provided in an embodiment of the present application;

[0042] Figure 8 A flow chart of an operating status evaluation process of a cable-structured flexible photovoltaic support provided in an embodiment of the present application;

[0043] Fig. 9 A structural schematic diagram of an amplitude displacement quantization model training device for a cable-structured flexible photovoltaic support provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] As described above, the existing cable-structured flexible photovoltaic bracket has a more complex structure, and its wind-vibration characteristics are difficult to effectively simulate through numerical simulation. It is also difficult to quantify the vibration of the cable-structured photovoltaic bracket, resulting in an inability to accurately evaluate the impact of vibration on power generation efficiency and component life.

[0045] Based on this, there is an urgent need for a high-precision method to quantify the vibration of cable-structured photovoltaic brackets, so as to achieve low-cost and high-precision monitoring of the amplitude displacement of cable-structured flexible photovoltaic brackets.

[0046] After research, the inventor proposed a method and device for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic bracket. A six-axis sensor is arranged on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket. The six-axis sensor can be used to monitor the motion state information of the cable-structured flexible photovoltaic bracket in three-dimensional space. The six-axis sensor is used to obtain historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information. Then, based on the vibration video information, the actual amplitude displacement information of the cable-structured flexible photovoltaic bracket in the historical period is determined. Finally, based on the historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic bracket in three-dimensional space. The initial neural network model is iteratively trained based on the information to obtain the amplitude-displacement quantification model; wherein, the historical main cable structure parameters are the structure parameters of the main cable in the historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable-structured flexible photovoltaic bracket in the historical period, the vibration video information is used to characterize the actual vibration of the cable-structured flexible photovoltaic bracket in the historical period, the target area is the area where the cable-structured flexible photovoltaic bracket is located, and the amplitude-displacement quantification model is used to determine the amplitude displacement of the cable-structured flexible photovoltaic bracket based on the main cable structure parameters, motion state information and meteorological information.

[0047] In the technical solution of the present application, since the middle of a single span is usually the position where the deflection of the cable-structured flexible photovoltaic bracket is the largest and the amplitude is the most obvious, by setting a six-axis sensor on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket, the vibration of the cable-structured flexible photovoltaic bracket can be captured more accurately; since the vibration video information can characterize the actual vibration of the cable-structured flexible photovoltaic bracket in a historical period, the actual amplitude displacement information of the cable-structured flexible photovoltaic bracket can be accurately determined based on the vibration video information, and thus the initial neural network model is iteratively trained based on the historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, so as to obtain a high-precision amplitude displacement quantification model; and then, it is only necessary to deploy a six-axis sensor on the cable-structured flexible photovoltaic bracket, and the amplitude displacement of the cable-structured flexible photovoltaic bracket can be accurately determined through the trained amplitude displacement quantification model based on the motion state information collected by the six-axis sensor and the main cable structure parameters and meteorological information corresponding to the cable-structured flexible photovoltaic bracket, thereby realizing high-precision amplitude displacement monitoring by deploying a single six-axis sensor, and reducing the vibration monitoring cost of the cable-structured flexible photovoltaic bracket.

[0048] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] Method Embodiment

[0050] An embodiment of the present application provides an embodiment of an amplitude displacement quantization model training method for a cable-structured flexible photovoltaic bracket, wherein a six-axis sensor is provided on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket; the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic bracket in three-dimensional space.

[0051] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0052] See also Figure 1 , which is a flow chart of a method for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic support provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0053] Step S101, obtaining historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information.

[0054] In an optional embodiment, an amplitude displacement quantization system can be used as the execution subject of the amplitude displacement quantization model training method of the cable-structured flexible photovoltaic support of the embodiment of the present application. For the convenience of description, the amplitude displacement quantization system is referred to as the system below.

[0055] In the embodiments of the present application, Figure 2As shown, the amplitude displacement quantification system may include a photovoltaic support information acquisition module and a photovoltaic support vibration detection module. The photovoltaic support information acquisition module transmits the collected data to the photovoltaic support vibration detection module by wired / wireless communication, and the photovoltaic support vibration detection module is used to quantify the amplitude displacement of the cable-structured flexible photovoltaic support through an amplitude displacement quantification model; the photovoltaic support information acquisition module includes a first information acquisition unit and a second information acquisition unit, wherein the first information acquisition unit is composed of a six-axis sensor and a matching RTU (full name: Remote Terminal Unit) collector, which is used to monitor the acceleration and angular velocity of the cable-structured flexible photovoltaic support in three-dimensional space; the second information acquisition unit is composed of a first visual sensor and a second visual sensor, the first visual sensor is used to collect the longitudinal vibration video of the cable-structured flexible photovoltaic support, and the second visual sensor is used to collect the lateral vibration video of the cable-structured flexible photovoltaic support.

[0056] In step S101, the historical main cable structure parameters are the structure parameters of the main cable in the historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable structure flexible photovoltaic bracket in the historical period, the vibration video information is used to characterize the actual vibration condition of the cable structure flexible photovoltaic bracket in the historical period, and the target area is the area where the cable structure flexible photovoltaic bracket is located.

[0057] Optionally, the vibration video information includes the longitudinal vibration video collected by the first visual sensor within the historical period, and the lateral vibration video collected by the second visual sensor within the historical period. The first visual sensor is located on the side of the single span of the cable-structured flexible photovoltaic support, and the second visual sensor is located below the middle of the single span of the cable-structured flexible photovoltaic support. The centers of the images collected by the first visual sensor and the second visual sensor are both where the six-axis sensor is located.

[0058] In order to collect accurate and clear vibration video, in the embodiment of the present application, a Figure 3The cable-structured flexible photovoltaic support test field shown in the figure, the cable-structured flexible photovoltaic support in the test field is composed of a first visual sensor, a second visual sensor, a six-axis sensor, a main cable, a photovoltaic module, a support beam and a support column. Among them, the six-axis sensor is arranged on the main cable in the middle of a single span of the cable-structured flexible photovoltaic support, the X-axis of the six-axis sensor is in the same direction as the support beam of the cable-structured flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the first visual sensor is located on the side of the single span of the cable-structured flexible photovoltaic support, and its installation height is consistent with the installation height of the six-axis sensor; the second visual sensor is located below the middle of the single span of the cable-structured flexible photovoltaic support, and the center of the picture collected by the first visual sensor and the second visual sensor is the position where the six-axis sensor is located.

[0059] It should be noted that since the middle of a single span is usually the position where the deflection of the entire cable-structured flexible photovoltaic bracket is the largest and the amplitude is the most obvious, by setting a six-axis sensor on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket, the vibration of the cable-structured flexible photovoltaic bracket (i.e., acceleration information and angular velocity information) can be more accurately captured, thereby providing more precise data for the quantification of the amplitude displacement.

[0060] Optionally, the motion state information includes: acceleration information of the cable-structured flexible photovoltaic support along the X-axis, Y-axis and Z-axis respectively, and angular velocity information of the cable-structured flexible photovoltaic support along the X-axis, Y-axis and Z-axis respectively.

[0061] In the embodiment of the present application, the six-axis sensor can collect the acceleration information and angular velocity information of the cable-structured flexible photovoltaic bracket along the X-axis, Y-axis and Z-axis in real time at a sampling frequency of >10H.

[0062] Optionally, the historical main cable structural parameters include the inclination angle between the main cable and the ground, the load-bearing capacity and the length of the main cable in the historical period; the meteorological information includes wind speed information and wind direction information.

[0063] In the embodiment of the present application, the wind speed information and wind direction information are data collected by the meteorological sensor of the photovoltaic station to which the cable-structure flexible photovoltaic support belongs.

[0064] Step S102, based on the vibration video information, determining the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period.

[0065] Optionally, the actual amplitude displacement information includes actual longitudinal amplitude displacement (i.e., amplitude displacement in the up and down directions when the cable structure flexible photovoltaic support vibrates) and actual lateral amplitude displacement (i.e., amplitude displacement in the left and right directions when the cable structure flexible photovoltaic support vibrates).

[0066] In order to achieve high-precision amplitude displacement quantification, in the embodiment of the present application, the system can perform video analysis on the vibration video information in the historical period to obtain accurate actual amplitude displacement information of the cable structure flexible photovoltaic support in the historical period. Figure 4 , Figure 4 A flowchart of a process for determining actual amplitude displacement information provided in an embodiment of the present application, the process comprising the following steps:

[0067] Step S1021, obtaining a first camera parameter, a second camera parameter, a first target distance, and a second target distance.

[0068] In step S1021, the first camera parameter is the internal parameter of the first visual sensor (for example, camera parameters: focal length, resolution, field of view, pixel size and other parameters), the second camera parameter is the internal parameter of the second visual sensor, the first target distance is the distance between the first visual sensor and the six-axis sensor, and the second target distance is the distance between the second visual sensor and the six-axis sensor.

[0069] Step S1022: Based on the first camera parameter and the first target distance, perform video analysis on the longitudinal vibration video to obtain an actual longitudinal amplitude displacement.

[0070] Step S1023: Based on the second camera parameter and the second target distance, perform video analysis on the lateral vibration video to obtain an actual lateral amplitude displacement.

[0071] In an embodiment of the present application, the system may store historical motion state information, actual amplitude displacement information, historical main cable structure parameters and historical meteorological information into a sample data set according to specified time series slices (eg, millisecond level or second level).

[0072] Optionally, the system can divide the sample data set into a training set, a validation set, and a test set to provide accurate sample data for iterative model training.

[0073] Step S103, based on historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, the initial neural network model is iteratively trained to obtain an amplitude displacement quantization model.

[0074] In step S103, the amplitude displacement quantification model is used to determine the amplitude displacement of the cable-structured flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information. The amplitude displacement includes lateral amplitude displacement (i.e., the amplitude displacement in the left-right direction when the cable-structured flexible photovoltaic support vibrates) and longitudinal amplitude displacement (i.e., the amplitude displacement in the up-down direction when the cable-structured flexible photovoltaic support vibrates).

[0075] Optionally, the main cable structural parameters include the inclination angle between the main cable and the ground, the load-bearing capacity and length of the main cable; the meteorological information includes wind speed information and wind direction information.

[0076] In order to obtain a high-precision amplitude displacement quantification model, so as to realize high-precision amplitude displacement monitoring by deploying a six-axis sensor separately, in the embodiment of the present application, Figure 5 As shown, the system can iteratively train the initial neural network model based on the historical motion state information collected by the six-axis sensor and the supporting RTU collector, as well as the historical main cable structure parameters, historical meteorological information and actual amplitude displacement information, to obtain a high-precision amplitude displacement quantization model. Among them, the initial neural network model can be any one of the neural network models such as the convolutional neural network model, the feedforward neural network model, the recurrent neural network model and the symmetric neural network model, which can be selected according to actual needs, so it is not specifically limited here.

[0077] In order to realize high-precision and low-cost amplitude displacement monitoring of the cable-structured flexible photovoltaic support, in this embodiment, Figure 6 As shown in the figure, in the actual amplitude displacement monitoring scenario of the cable-structured flexible photovoltaic support, only the necessary components such as the six-axis sensor, the main cable, the photovoltaic module, the support beam and the support column need to be set in the cable-structured flexible photovoltaic support to achieve high-precision amplitude displacement monitoring; wherein, the six-axis sensor is set on the main cable in the middle of the single span of the cable-structured flexible photovoltaic support, that is, the six-axis sensor is set in a section of flexible photovoltaic module installation interval without interruption, and is located at the monitoring point in the center of the main cable in the interval. This position is the position where the deflection of the cable-structured flexible photovoltaic support is the largest and the amplitude is the most obvious; the X-axis of the six-axis sensor is in the same direction as the support beam of the cable-structured flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable.

[0078] In order to achieve high-precision amplitude displacement quantization, in the embodiment of the present application, Figure 7 As shown, the system can input the meteorological information of the target area at the target time, the main cable structure parameters of the main cable at the target time, and the motion state information collected by the six-axis sensor and the supporting RTU collector at the target time into the pre-trained amplitude displacement quantification model. The amplitude displacement quantification model obtains the amplitude displacement of the cable structure flexible photovoltaic bracket at the target time through its input layer, neuron layer and output layer.

[0079] It should be noted that, by quantifying the amplitude displacement of the cable-structured flexible photovoltaic bracket through a pre-trained amplitude displacement quantification model, high-precision amplitude displacement monitoring can be achieved by separately deploying a six-axis sensor, thereby reducing the vibration monitoring cost of the cable-structured flexible photovoltaic bracket; avoiding the problem of only installing a six-axis sensor to monitor the cable-structured flexible photovoltaic bracket, which leads to the inability to meet the user's business needs for intuitive, quantifiable and measurable monitoring information, thereby improving the user experience.

[0080] In order to avoid the problem of affecting the power generation efficiency and component life of the cable-structured flexible photovoltaic support due to the inability to timely determine that the operating state of the cable-structured flexible photovoltaic support is an abnormal state, and to improve the power generation efficiency and component life of the cable-structured flexible photovoltaic support, in the embodiment of the present application, after determining the amplitude displacement of the cable-structured flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information, the system can perform data analysis on the motion state information collected by the six-axis sensor at the target time, as well as the meteorological information, the main cable structure parameters and the amplitude displacement output by the amplitude displacement quantization model, so as to evaluate the operating state of the cable-structured flexible photovoltaic support. Specifically, Figure 8 As shown, the process includes the following steps:

[0081] Step S801, constructing a time series data table based on motion state information, meteorological information, main cable structure parameters and amplitude displacement.

[0082] Step S802, performing data analysis on the time series data table to obtain analysis results; the analysis results are used to evaluate the operating status of the cable structure flexible photovoltaic support.

[0083] In an embodiment of the present application, the system can perform XY curve analysis, waveform mutation analysis and other diagnoses on the timing data table, evaluate the operating status of the cable-structured flexible photovoltaic bracket, and determine whether the vibration displacement of the cable-structured flexible photovoltaic bracket is within the normal range, thereby achieving timely early warning of abnormal operating status of the cable-structured flexible photovoltaic bracket, and avoiding the problem of affecting the power generation efficiency and component life of the cable-structured flexible photovoltaic bracket due to the inability to timely determine that the operating status of the cable-structured flexible photovoltaic bracket is an abnormal state.

[0084] By using the amplitude displacement quantification model training method for the cable-structured flexible photovoltaic bracket provided in the embodiment of the present application, a six-axis sensor is set on the main cable in the middle of a single span of the cable-structured flexible photovoltaic bracket, so that the vibration of the cable-structured flexible photovoltaic bracket can be captured more accurately; by iteratively training the initial neural network model based on historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information, a high-precision amplitude displacement quantification model can be obtained; thus, it is only necessary to deploy a six-axis sensor on the cable-structured flexible photovoltaic bracket to accurately determine the amplitude displacement of the cable-structured flexible photovoltaic bracket through the trained amplitude displacement quantification model based on the motion state information collected by the six-axis sensor and the main cable structure parameters and meteorological information corresponding to the cable-structured flexible photovoltaic bracket, thereby realizing high-precision amplitude displacement monitoring by deploying a single six-axis sensor, reducing the vibration monitoring cost of the cable-structured flexible photovoltaic bracket; avoiding the problem of only installing a six-axis sensor to monitor the cable-structured flexible photovoltaic bracket, which leads to the inability to meet the user's business needs for intuitive, quantifiable and measurable monitoring information, thereby improving the user experience.

[0085] Device Embodiment

[0086] The embodiment of the present application provides an amplitude displacement quantization model training device for a cable-structured flexible photovoltaic support, wherein a six-axis sensor is provided on the main cable in the middle of a single span of the cable-structured flexible photovoltaic support, and the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic support in three-dimensional space. Fig. 9 A schematic diagram of the structure of an amplitude displacement quantization model training device for a cable-structured flexible photovoltaic support provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, the device includes an acquisition module 11, a determination module 12 and a training module 13. Fig. 9 You can see the connection relationship between several modules.

[0087] Among them, the acquisition module 11 is used to obtain historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; the historical main cable structure parameters are the structure parameters of the main cable in the historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable structure flexible photovoltaic bracket in the historical period, the vibration video information is used to characterize the actual vibration of the cable structure flexible photovoltaic bracket in the historical period, and the target area is the area where the cable structure flexible photovoltaic bracket is located;

[0088] A determination module 12 is used to determine the actual amplitude displacement information of the cable structure flexible photovoltaic support within a historical period based on the vibration video information;

[0089] The training module 13 is used to iteratively train the initial neural network model based on historical main cable structure parameters, historical meteorological information, historical motion state information and actual amplitude displacement information to obtain an amplitude displacement quantification model; the amplitude displacement quantification model is used to determine the amplitude displacement of the cable structure flexible photovoltaic bracket based on the main cable structure parameters, motion state information and meteorological information.

[0090] Optionally, the X-axis of the six-axis sensor is in the same direction as the support beam of the cable-structured flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the motion state information includes:

[0091] Acceleration information of the cable-structured flexible photovoltaic bracket along the X-axis, Y-axis and Z-axis respectively;

[0092] Angular velocity information of the cable-structured flexible photovoltaic bracket along the X-axis, Y-axis and Z-axis respectively.

[0093] Optionally, the main cable structural parameters include the inclination angle between the main cable and the ground, the load-bearing capacity and length of the main cable; the meteorological information includes wind speed information and wind direction information.

[0094] Optionally, the vibration video information includes the longitudinal vibration video collected by the first visual sensor within the historical period, and the lateral vibration video collected by the second visual sensor within the historical period. The first visual sensor is located on the side of the single span of the cable-structured flexible photovoltaic support, and the second visual sensor is located below the middle of the single span of the cable-structured flexible photovoltaic support. The centers of the images collected by the first visual sensor and the second visual sensor are both where the six-axis sensor is located.

[0095] Optionally, the determination module includes: a data acquisition unit, a first determination unit and a second determination unit.

[0096] The data acquisition unit is used to acquire a first camera parameter, a second camera parameter, a first target distance, and a second target distance; the first camera parameter is an internal parameter of the first visual sensor, the second camera parameter is an internal parameter of the second visual sensor, the first target distance is the distance between the first visual sensor and the six-axis sensor, and the second target distance is the distance between the second visual sensor and the six-axis sensor;

[0097] A first determination unit is used to perform video analysis on the longitudinal vibration video based on the first camera parameter and the first target distance to obtain an actual longitudinal amplitude displacement;

[0098] The second determining unit is used to perform video analysis on the lateral vibration video based on the second camera parameter and the second target distance to obtain an actual lateral amplitude.

[0099] Optionally, the amplitude displacement quantification model training device of the cable-structured flexible photovoltaic support also includes: a data table construction module and a data analysis module.

[0100] The data table construction module is used to construct a time series data table based on the motion state information, meteorological information, main cable structure parameters and amplitude displacement after determining the amplitude displacement of the cable structure flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information;

[0101] The data analysis module is used to perform data analysis on the time series data table to obtain analysis results; the analysis results are used to evaluate the operating status of the cable structure flexible photovoltaic support.

[0102] Storage Medium Embodiments

[0103] The embodiment of the present application provides a computer-readable storage medium, on which a program is stored, wherein when the program is executed by a processor, some or all of the steps in the amplitude displacement quantization model training method of the cable-structured flexible photovoltaic support introduced in the aforementioned method embodiment of the present application are implemented. The storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0104] Processor Embodiments

[0105] An embodiment of the present application provides a processor for running a program, wherein, when the program is running, some or all of the steps in the amplitude displacement quantization model training method of the cable-structured flexible photovoltaic support introduced in the aforementioned method embodiment are executed.

[0106] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely schematic, in which the unit described as a separate component may or may not be physically separated, and the component prompted as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic support, characterized in that: A six-axis sensor is provided on the main cable in the middle of a single span of the cable-structured flexible photovoltaic support, and the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic support in a three-dimensional space. The method comprises: Acquire historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; the historical main cable structure parameters are the structure parameters of the main cable in the historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable structure flexible photovoltaic bracket in the historical period, the vibration video information is used to characterize the actual vibration of the cable structure flexible photovoltaic bracket in the historical period, and the target area is the area where the cable structure flexible photovoltaic bracket is located; the vibration video information includes the longitudinal vibration video collected by the first visual sensor in the historical period, and the lateral vibration video collected by the second visual sensor in the historical period, and the center of the picture collected by the first visual sensor and the second visual sensor is the position where the six-axis sensor is located; Based on the vibration video information, determining the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period; Based on the historical main cable structure parameters, the historical meteorological information, the historical motion state information and the actual amplitude displacement information, the initial neural network model is iteratively trained to obtain an amplitude displacement quantization model; the amplitude displacement quantization model is used to determine the amplitude displacement of the cable structure flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information; The actual amplitude displacement information includes the actual longitudinal amplitude displacement and the actual lateral amplitude displacement, and the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period is determined based on the vibration video information, including: Acquire a first camera parameter, a second camera parameter, a first target distance, and a second target distance; the first camera parameter is an internal parameter of the first visual sensor, the second camera parameter is an internal parameter of the second visual sensor, the first target distance is a distance between the first visual sensor and the six-axis sensor, and the second target distance is a distance between the second visual sensor and the six-axis sensor; Based on the first camera parameter and the first target distance, performing video analysis on the longitudinal vibration video to obtain the actual longitudinal amplitude displacement; Based on the second camera parameter and the second target distance, video analysis is performed on the lateral vibration video to obtain the actual lateral amplitude displacement.

2. The method according to claim 1, characterized in that The X-axis of the six-axis sensor is in the same direction as the support beam of the cable structure flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the motion state information includes: Acceleration information of the cable-structured flexible photovoltaic support along the X-axis, the Y-axis and the Z-axis respectively; The cable-structured flexible photovoltaic support has angular velocity information along the X-axis, the Y-axis and the Z-axis respectively.

3. The method according to claim 1, characterized in that The main cable structural parameters include the inclination angle between the main cable and the ground, the load-bearing capacity and length of the main cable; the meteorological information includes wind speed information and wind direction information.

4. The method according to claim 1, characterized in that The first visual sensor is located on the side of the single span of the cable structure flexible photovoltaic support, and the second visual sensor is located below the middle of the single span of the cable structure flexible photovoltaic support.

5. The method according to claim 1, characterized in that After determining the amplitude displacement of the cable structure flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information, the method further includes: Constructing a time series data table based on the motion state information, the meteorological information, the main cable structure parameters and the amplitude displacement; Data analysis is performed on the time series data table to obtain analysis results; the analysis results are used to evaluate the operating status of the cable structure flexible photovoltaic support.

6. A device for training an amplitude displacement quantization model of a cable-structured flexible photovoltaic support, characterized in that: A six-axis sensor is provided on the main cable in the middle of a single span of the cable-structured flexible photovoltaic support, and the six-axis sensor is used to monitor the motion state information of the cable-structured flexible photovoltaic support in a three-dimensional space. The device includes: An acquisition module is used to acquire historical main cable structure parameters, historical meteorological information, historical motion state information and vibration video information; the historical main cable structure parameters are the structure parameters of the main cable in a historical period, the historical meteorological information is the meteorological information of the target area in the historical period, the historical motion state information is the motion state information of the cable structure flexible photovoltaic support in the historical period, and the vibration video information is used to characterize the actual vibration of the cable structure flexible photovoltaic support in the historical period, and the target area is the area where the cable structure flexible photovoltaic support is located; the vibration video information includes the longitudinal vibration video collected by the first visual sensor in the historical period, and the lateral vibration video collected by the second visual sensor in the historical period, and the center of the picture collected by the first visual sensor and the second visual sensor is the position where the six-axis sensor is located; A determination module, used to determine the actual amplitude displacement information of the cable structure flexible photovoltaic support within the historical period based on the vibration video information; the actual amplitude displacement information includes the actual longitudinal amplitude displacement and the actual lateral amplitude displacement; A training module, for iteratively training the initial neural network model based on the historical main cable structure parameters, the historical meteorological information, the historical motion state information and the actual amplitude displacement information to obtain an amplitude displacement quantization model; the amplitude displacement quantization model is used to determine the amplitude displacement of the cable structure flexible photovoltaic support based on the main cable structure parameters, motion state information and meteorological information; Wherein, the determination module includes: a data acquisition unit, configured to acquire a first camera parameter, a second camera parameter, a first target distance, and a second target distance; the first camera parameter is an internal parameter of the first visual sensor, the second camera parameter is an internal parameter of the second visual sensor, the first target distance is a distance between the first visual sensor and the six-axis sensor, and the second target distance is a distance between the second visual sensor and the six-axis sensor; A first determining unit, configured to perform video analysis on the longitudinal vibration video based on the first camera parameter and the first target distance to obtain the actual longitudinal amplitude displacement; The second determining unit is used to perform video analysis on the lateral vibration video based on the second camera parameter and the second target distance to obtain the actual lateral amplitude displacement.

7. The device according to claim 6, characterized in that The X-axis of the six-axis sensor is in the same direction as the support beam of the cable structure flexible photovoltaic support, the Y-axis of the six-axis sensor is in the same direction as the main cable, the Z-axis of the six-axis sensor is perpendicular to the direction of the main cable, and the direction of the support beam is perpendicular to the direction of the main cable; the motion state information includes: Acceleration information of the cable-structured flexible photovoltaic support along the X-axis, the Y-axis and the Z-axis respectively; The cable-structured flexible photovoltaic support has angular velocity information along the X-axis, the Y-axis and the Z-axis respectively.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the amplitude displacement quantization model training method of the cable-structured flexible photovoltaic support according to any one of claims 1 to 5 is implemented.

9. A processor, characterized in that: Used to run a computer program, which, when running, executes the amplitude displacement quantization model training method for the cable-structured flexible photovoltaic support according to any one of claims 1 to 5.

Images